Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ляє
    -0.07
     бактер
    -0.06
    یه
    -0.06
     capac
    -0.06
     सक
    -0.06
    μένων
    -0.06
     أح
    -0.06
    /cli
    -0.06
    Like
    -0.06
    φα
    -0.06
    POSITIVE LOGITS
     inheritance
    0.06
     Mez
    0.06
     assumed
    0.06
    cookie
    0.06
    dba
    0.06
     trunc
    0.06
    _attribute
    0.06
    archives
    0.06
    prav
    0.06
    (distance
    0.06
    Act Density 0.059%

    No Known Activations